SPGISpeech 2.0: Transcribed multi-speaker financial audio for speaker-tagged transcription

TL;DR

SPGISpeech 2.0 is a large, diverse dataset of transcribed financial earnings calls designed to improve multi-speaker speech recognition models in the financial domain.

Contribution

The paper introduces SPGISpeech 2.0, a new dataset with 3,780 hours of transcribed financial audio, including speaker and call info, enhancing multi-talker ASR research.

Findings

Improved speaker-tagged ASR performance after fine-tuning on the dataset.

Dataset enables new research in multi-talker financial speech recognition.

Released freely for non-commercial research use.

Abstract

We introduce SPGISpeech 2.0, a dataset suitable for speaker-tagged transcription in the financial domain. SPGISpeech 2.0 improves the diversity of applicable modeling tasks while maintaining the core characteristic of the original SPGISpeech dataset: audio snippets and their corresponding fully formatted text transcriptions, usable for end-to-end automatic speech recognition (ASR). SPGISpeech 2.0 consists of 3,780 additional hours of professionally transcribed earnings calls. Furthermore, the dataset contains call and speaker information for each audio snippet facilitating multi-talker ASR. We validate the utility of SPGISpeech 2.0 through improvements in speaker-tagged ASR performance of popular speech recognition models after fine-tuning on SPGISpeech 2.0. Released free for non-commercial use, we expect SPGISpeech 2.0 to foster advancements in speech recognition technologies and inspire a wide range of research applications.